meta-ads-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes advertising data (campaign names, ad copy, audience names) retrieved from the Meta Ads API, which acts as an external ingestion point for untrusted content.
- Ingestion points: Data returned by
meta_ads__tool_get_campaigns,meta_ads__tool_get_ads, andmeta_ads__tool_get_custom_audiencesinSKILL.md. - Boundary markers: The skill does not define specific delimiters to wrap external data, though it instructs the agent to use the data for specific reporting structures.
- Capability inventory: The skill uses
WebFetch,WebSearch, and specialized Meta Ads tools for data retrieval and reporting. - Sanitization: No explicit sanitization or filtering of API responses is mentioned in the instructions.
Audit Metadata